Patterns, Predictions, and Actions: A Story About Machine Learning

by Moritz Hardt, Benjamin Recht

This graduate textbook on machine learning tells a story of how patterns in data support predictions and consequential actions. Starting with the foundations of decision making, we cover representation, optimization, and generalization as the constituents of supervised learning. A chapter on datasets as benchmarks examines their histories and scientific bases. Self-contained introductions to causality, the practice of causal inference, sequential decision making, and reinforcement learning equip the reader with concepts and tools to reason about actions and their consequences. Throughout, the text discusses the historical context and societal impact. We invite readers from all backgrounds; some experience with probability, calculus, and linear algebra suffice.

Genres: Technology, Textbooks, Nonfiction, Artificial Intelligence, Computer Science

296 pages, ebook

Published February 10, 2021

Reviews

[Simone Scardapane · Rating 5 out of 5]

If you like machine learning, you have to read this one. It's a modern introduction including a lot of novel ideas on generalization and optimization, as long as two chapters on causal inference and more references and historical footnotes that I can count. Way too dense at times, but it can benefit both novices and experienced readers at the same time.

[Rob Romijnders · Rating 4 out of 5]

Refreshing read, I enjoyed this one a lot. Even after five years in the field -and two years of PhD- I learned from the common threads and links being made between the various chapters.

Edit in April 2023: current author list on Goodreads only mentions Moritz Hardt. I think also Benjamin Recht should be listed.